AnchorBench: A Multi-Pathway Benchmark for the Anchoring Effect in LLMs
The anchoring effect is a cognitive bias in which an initial reference value shifts a later judgment toward itself. This effect is well established in human judgment and decision-making, and recent work suggests that large language models (LLMs) exhibit similar behavior. However, existing work on anchoring in LLMs typically evaluates only a narrow set of anchor pathways and rarely distinguishes irrelevant from plausible anchors. We introduce AnchorBench, a benchmark for the anchoring effect in LLMs that evaluates multiple anchor pathways under an explicit anchor relevance axis. Across fourteen
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 47%Understanding large language models demands distinguishing human projection from machine cognition - Nature →
- FuzzySimilar title/name (fuzzy) · 59%jeinlee1991/chinese-llm-benchmark →
“Fuzzy title match (0.73): “AnchorBench: A Multi-Pathway Benchmark for the Anchoring Eff” ≈ “jeinlee1991/chinese-llm-benchmark””
- LinkedLinked via arxiv author · 85%Yiderigun Borjigin →
“AnchorBench: A Multi-Pathway Benchmark for the Anchoring Effect in LLMs”
- LinkedLinked via arxiv author · 85%Alexander Hermann →
“AnchorBench: A Multi-Pathway Benchmark for the Anchoring Effect in LLMs”
- LinkedLinked via arxiv author · 85%Christian Cyron →
“AnchorBench: A Multi-Pathway Benchmark for the Anchoring Effect in LLMs”
- LinkedLinked via arxiv author · 85%Roland Aydin →
“AnchorBench: A Multi-Pathway Benchmark for the Anchoring Effect in LLMs”